Research on multi-camera information fusion method for intelligent perception

In this paper, the Gaussian Mixture Model and Mean Shift algorithm are used to detect and track moving objects in the visual perception network composed of multiple cameras. And on this basis, a target matching method based on wavelet transform, which is applied in a visual perception network composed by multiple camera, fusing visual information from different cameras is proposed. This method takes local features as basis of target matching, and applies wavelet transformation to detect the feature points that represent important information of the target image, and then extracts the color of the neighborhood of feature points as its salient features. The method of classification and clustering is applied by calculating the distance of salient features vector space to measure similarities of the target features and thus realize target recognition. The test result shows that the method can realize the matching and recognition of moving object with the cooperation among multiple cameras.

[1]  Zhiping Zhou,et al.  Target tracking based on foreground probability , 2014, Multimedia Tools and Applications.

[2]  K. V. Sriharsha,et al.  Dynamic scene analysis using Kalman filter and mean shift tracking algorithms , 2015, 2015 6th International Conference on Computing, Communication and Networking Technologies (ICCCNT).

[3]  Fakhri Karray,et al.  Recent Advances on Context-Awareness and Data/Information Fusion in ITS , 2014, International Journal of Intelligent Transportation Systems Research.

[4]  Zhang Yi,et al.  Multimodal data fusion model for smart city , 2016 .

[5]  Anna Corinna Cagliano,et al.  Current trends in Smart City initiatives: some stylised facts , 2014 .

[6]  Rekha R. Thomas,et al.  The Euclidean Distance Degree of an Algebraic Variety , 2013, Foundations of Computational Mathematics.

[7]  Shuai Liu,et al.  A review of visual moving target tracking , 2017, Multimedia Tools and Applications.

[8]  Xu Yang,et al.  Moving region detection based on background difference , 2014, 2014 IEEE Workshop on Electronics, Computer and Applications.

[9]  Huadong Guo,et al.  Digital Earth 2020: towards the vision for the next decade , 2012, Int. J. Digit. Earth.

[10]  Shailaja Surkutlawar,et al.  Shadow Suppression using RGB and HSV Color Space in Moving Object Detection , 2013 .

[11]  Booncharoen Sirinaovakul,et al.  Feature Point Matching with Matching Distribution , 2015 .

[12]  Rong Chen.  Image segmentation and target tracking based on meanshift algorithm , 2015 .

[13]  Yuriy Mishchenko,et al.  A fast algorithm for computation of discrete Euclidean distance transform in three or more dimensions on vector processing architectures , 2013, Signal, Image and Video Processing.

[14]  Ashok Kumar,et al.  Neural Networks for Fast Estimation of Social Network Centrality Measures , 2015 .

[15]  Christophe Ducottet,et al.  A wavelet based multiscale detection scheme of feature points , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Fandy Setyo Utomo,et al.  Multiple Vehicle Tracking using Adaptive Gaussian Mixture Model and Kalman Filter , 2016 .

[17]  Natapon Pantuwong,et al.  A comparative study of feature point matching versus foreground detection for computer detection of dairy cows in video frames , 2015, Artificial Life and Robotics.

[18]  Leo Liberti,et al.  Euclidean Distance Geometry and Applications , 2012, SIAM Rev..

[19]  Michal Kawulok,et al.  Hand landmarks detection and localization in color images , 2016, Multimedia Tools and Applications.

[20]  M. A. A. Mamun,et al.  A Comparative Study of Wavelet Transform and Fourier Transform , 2011 .

[21]  About the Mean Difference of the Inverse Normal Distribution , 2016 .

[22]  Yuqiu Sun,et al.  Local Feature Image Fusion Algorithm Based on Wavelet Transform , 2012 .

[23]  Jürgen Popp,et al.  Separation of CARS image contributions with a Gaussian mixture model. , 2010, Journal of the Optical Society of America. A, Optics, image science, and vision.

[24]  G. Yamuna,et al.  Real time implementation of RGB to HSV/HSI/HSL and its reverse color space models , 2016, 2016 International Conference on Communication and Signal Processing (ICCSP).

[25]  Gandham Sindhuja,et al.  Comparative analysis of mean shift in object tracking , 2015, 2015 Conference on Power, Control, Communication and Computational Technologies for Sustainable Growth (PCCCTSG).

[26]  Ronald R. Yager,et al.  Multi-source Information Fusion Using Measure Representations , 2016, On Logical, Algebraic, and Probabilistic Aspects of Fuzzy Set Theory.

[27]  Brian Peacock,et al.  Normal (Gaussian) Distribution , 2010 .

[28]  Nor Badrul Anuar,et al.  The role of big data in smart city , 2016, Int. J. Inf. Manag..

[29]  R. S. Pathak,et al.  Distributional Wavelet Transform , 2016 .

[30]  Jiamin Zheng,et al.  An Improved Moving Object Detection Algorithm Based on Gaussian Mixture Models , 2016 .

[31]  Dileep Kumar Yadav,et al.  Efficient method for moving object detection in cluttered background using Gaussian Mixture Model , 2014, 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[32]  Christian Callegari,et al.  Advances in Computing, Communications and Informatics (ICACCI) , 2015 .

[33]  Liana Stanescu,et al.  A New Method for Segmentation of Images Represented in a HSV Color Space , 2009, ACIVS.

[34]  Ying Zheng,et al.  Performance Analysis of a Moving Target Tracking Method Based on Computer Vision , 2016, 2016 Eighth International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).

[35]  Yu Liu,et al.  Robust Image Feature Point Matching Based on Structural Distance , 2015, IGTA.

[36]  Lin Li,et al.  A novel background-weighted histogram scheme based on foreground saliency for mean-shift tracking , 2015, Multimedia Tools and Applications.

[37]  Zhang Yi,et al.  Double Gaussian mixture model for image segmentation with spatial relationships , 2016, J. Vis. Commun. Image Represent..

[38]  Yonghuai Liu,et al.  Performance Evaluation of Video Summaries Using Efficient Image Euclidean Distance , 2016, ISVC.

[39]  M. M. Naushad Ali,et al.  Multiple object tracking with partial occlusion handling using salient feature points , 2014, Inf. Sci..

[40]  Suh-Yin Lee,et al.  A view-invariant and anti-reflection algorithm for car body extraction and color classification , 2012, Multimedia Tools and Applications.

[41]  S. Skoneczny.  Nonlinear image sharpening in the HSV color space , 2012 .

[42]  Charles F. F. Karney.  Sampling Exactly from the Normal Distribution , 2013, ACM Trans. Math. Softw..